KR20220130288A - Medical image process apparatus and medical image learning method, and medical image process method - Google Patents

Abstract

A medical image processing method performed by a medical image processing device according to one embodiment includes the steps of: inputting a body X-ray image of the heart of a diagnosis subject into a pre-learned artificial neural network model, estimating the type of an artificial valve in the heart of a body X-ray image as an output of the artificial neural network model, and obtaining shape information related to the artificial valve; estimating a blood flow direction of the heart based on the obtained shape information; and determining the type of the artificial valve as a result of re-estimating the type of the artificial valve based on the estimated type of the artificial valve and the estimated direction of blood flow.

Description

Medical image processing apparatus and its medical image learning method and medical image processing method

The present invention relates to a method and apparatus for learning a medical image of a body, and a method and apparatus for processing a medical image of the body.

A medical image refers to an image obtained by using a medical imaging device to include information on the internal structure of the body of a subject to be diagnosed. A medical imaging apparatus used to acquire such a medical image is a non-invasive examination apparatus, and displays structural details in the body, internal tissues and fluid flow, etc. by photographing and processing the image to the user. A user such as a doctor may diagnose a patient's health condition and disease by using a medical image output from the medical imaging apparatus. For example, as a medical imaging device, an X-ray imaging device that irradiates X-rays to an object and detects X-rays passing through the object to image an image, and a magnetic resonance imaging device for providing a magnetic resonance image. There are a magnetic resonance imaging (MRI) apparatus, a computed tomography (CT) apparatus, and an ultrasound (Ultrasound) diagnostic apparatus.

A prosthetic valve is implanted in a human or animal body and can be used, for example, as a passive one direct prosthetic valve in or near a blood vessel. The prosthetic valve may be completely preformed and implanted as is, or it may be formed in situ using artificial and/or natural components necessary to form a functional prosthetic valve.

These artificial valves can be broadly divided into mechanical valves and tissue valves according to materials, and depending on the location, a mitral valve, an aortic valve, a tricuspid valve, and It can be divided into pulmonary valves, etc. The artificial valves are also photographed in medical images taken of humans or animals with artificial valves, and medical practices, etc. For this, it is necessary to distinguish the types.

According to the prior art, the types of artificial valves included in the medical images were classified depending on the doctor's visual observation of the medical images. Accordingly, there was a problem in that the accuracy of classifying the types of artificial valves included in the medical image was changed.

Korean Patent Registration No. 10-1517752 (Registered on April 29, 2015)

According to the embodiment, there is provided a medical image processing method and apparatus capable of accurately distinguishing types of artificial valves included in a medical image by using an artificial neural network model and a learning technique thereof.

The problems to be solved of the present invention are not limited to those mentioned above, and other problems to be solved that are not mentioned will be clearly understood by those of ordinary skill in the art to which the present invention belongs from the following description.

In the medical image processing method performed by the medical image processing apparatus according to the first aspect, a body X-ray image of a heart of a diagnosis subject is input to a pre-trained artificial neural network model, and as an output of the artificial neural network model, the body estimating the type of the artificial valve in the heart of the X-ray image, obtaining shape information related to the artificial valve, estimating the blood flow direction of the heart based on the obtained shape information, and the estimated artificial valve and determining the type of the artificial valve as a result of re-estimating the type of the artificial valve based on the type of blood flow and the estimated blood flow direction.

According to the second aspect, when the computer program of a computer-readable recording medium storing a computer program is executed by a processor, instructions for causing the processor to perform the medical image processing method performed by the medical image processing apparatus include

According to a third aspect, a computer program stored in a computer-readable recording medium includes instructions for, when executed by a processor, to cause the processor to perform a medical image processing method performed by the medical image processing apparatus.

A method for learning a medical image of a medical image processing apparatus according to a fourth aspect comprises the steps of: preparing body X-ray images for heart training as an input constituting a first learning data set; and a label constituting the first learning data set preparing information on types of artificial valves and shape information related to the artificial valves respectively corresponding to the X-ray images of the body for learning, and a plurality of shape information and the plurality of shapes as inputs constituting a second learning data set Preparing cardiac blood flow direction information corresponding to the information, and preparing information on the type of artificial valve corresponding to the plurality of shape information and the cardiac blood flow direction information as a label constituting the second learning data set; and training a first layer of the artificial neural network model using the first training data set and training a second layer of the artificial neural network model using the second training data set.

According to a fifth aspect, the computer program on a computer-readable recording medium storing the computer program includes instructions for, when executed by a processor, to cause the processor to perform the method for learning a medical image of the medical image processing apparatus. .

According to a sixth aspect, a computer program stored in a computer-readable recording medium includes instructions for, when executed by a processor, to cause the processor to perform a method for learning a medical image of the medical image processing apparatus.

A medical image processing apparatus according to a seventh aspect includes an input unit for receiving a body X-ray image of a heart of a subject to be diagnosed, and an artificial neural network model using the body X-ray image of the subject to be diagnosed from the input unit received through the input unit. An artificial neural network model unit for estimating the type of artificial valve in the image and obtaining shape information related to the artificial valve, estimating the blood flow direction of the heart based on the obtained shape information, and determining the type of the estimated artificial valve and a processing unit that determines the type of the artificial valve as a result of re-estimating the type of the artificial valve based on the estimated blood flow direction; and an output unit that outputs information on the type of the artificial valve determined by the processing unit. .

A medical image processing apparatus according to an eighth aspect includes, as an input, body X-ray images for learning of a heart, and labels type information of an artificial valve corresponding to each of the body X-ray images for learning and shape information related to the artificial valve. a first learning data set including as an input, a plurality of shape information and cardiac blood flow direction information corresponding to the plurality of shape information as inputs, and a type of artificial valve corresponding to the plurality of shape information and the cardiac blood flow direction information An input unit for receiving a second training data set including information as a label, the first layer of the artificial neural network model learns the first training data set received through the input unit, and an artificial neural network model unit in which a second layer of the artificial neural network model learns a training data set.

According to an embodiment, types of artificial valves included in a medical image may be accurately distinguished by using an artificial neural network model and a learning technique thereof. By providing the medical personnel with information on the types of artificial valves classified using the artificial neural network model, it has the effect of supporting the medical personnel to accurately determine the end of the artificial valve included in the body X-ray image.

1 is a block diagram of a medical image processing apparatus according to an exemplary embodiment.
2 is a flowchart illustrating a process of learning an artificial neural network model of an artificial neural network model unit of a medical image processing apparatus according to a first embodiment of the present invention.
3 is a flowchart illustrating a process in which the medical image processing apparatus including the artificial neural network model learned according to the first embodiment of the present invention determines the type of the artificial valve in the heart of a diagnosis subject.
4 is a flowchart illustrating a process of learning the artificial neural network model of the artificial neural network model unit of the medical image processing apparatus according to the second embodiment of the present invention.
5 is a view showing the shape of a shadow for each type of artificial valve.

Advantages and features of the present invention and methods of achieving them will become apparent with reference to the embodiments described below in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various different forms, and only these embodiments allow the disclosure of the present invention to be complete, and common knowledge in the technical field to which the present invention pertains It is provided to fully inform those who have the scope of the invention, and the present invention is only defined by the scope of the claims.

Terms used in this specification will be briefly described, and the present invention will be described in detail.

The terms used in the present invention have been selected as currently widely used general terms as possible while considering the functions in the present invention, but these may vary depending on the intention or precedent of a person skilled in the art, the emergence of new technology, and the like. In addition, in a specific case, there is a term arbitrarily selected by the applicant, and in this case, the meaning will be described in detail in the description of the corresponding invention. Therefore, the term used in the present invention should be defined based on the meaning of the term and the overall content of the present invention, rather than the name of a simple term.

When a part 'includes' a certain component throughout the specification, this means that other components may be further included, rather than excluding other components, unless otherwise stated.

In addition, the term 'unit' used in the specification means software or a hardware component such as an FPGA or ASIC, and 'unit' performs certain roles. However, 'part' is not limited to software or hardware. The 'unit' may be configured to reside on an addressable storage medium or it may be configured to refresh one or more processors. Thus, as an example, 'part' refers to components such as software components, object-oriented software components, class components and task components, processes, functions, properties, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays and variables. Functions provided within components and 'units' may be combined into a smaller number of components and 'units' or further divided into additional components and 'units'.

Hereinafter, with reference to the accompanying drawings, the embodiments of the present invention will be described in detail so that those skilled in the art can easily carry out the embodiments of the present invention. And in order to clearly explain the present invention in the drawings, parts irrelevant to the description will be omitted.

In the present specification, a subject or patient to be diagnosed may include a human or an animal, or a part of a human or animal.

Also, in this specification, 'image' may mean multi-dimensional data composed of discrete image elements (eg, pixels in a two-dimensional image and voxels in a three-dimensional image). have.

The medical image processing apparatus, the medical image learning method and the medical image processing method of the present invention can be implemented in various embodiments, and in the following description, the first embodiment and the second embodiment will be representatively described. do it with 1 is a block diagram of a medical image processing apparatus 100 according to an embodiment of the present invention, and the illustrated medical image processing apparatus 100 performs a medical image learning method and a medical image processing method implemented in various forms. However, the description of the medical image processing apparatus 100 will be divided into a first embodiment and a second embodiment.

<First embodiment>

FIG. 1 shows a configuration of a medical image processing apparatus 100 according to an exemplary embodiment, but what is shown in FIG. 1 is merely exemplary. The medical image processing apparatus 100 may be implemented in a PC or a server or may include the same.

Referring to FIG. 1 , the medical image processing apparatus 100 includes an input unit 110 , an artificial neutral network model unit 120 , a processing unit 130 , and an output unit 140 .

The input unit 110 receives body X-ray images for heart training as an input constituting the training data set. In addition, the input unit 110 receives type information of the artificial valve in the heart of the body X-ray image and shape information related to the artificial valve as a label constituting the learning data set. Also, the input unit 110 receives a body X-ray image of the heart of the subject to be diagnosed. Here, the training data set is to be used when training the artificial neural network model unit 120 , and the body X-ray image of the heart of the diagnosis subject is input into the artificial neural network model unit 120 that has been previously learned and the type of artificial valve. is to determine

In the artificial neural network model unit 120 , the artificial neural network model learns the training data set received through the input unit 110 . And, the artificial neural network model unit 120 learned through the input unit 110, the artificial neural network model from the body X-ray image of the subject to be diagnosed, estimating the type of artificial valve in the body X-ray image, the form related to the artificial valve get information For example, the artificial neural network model unit 120 may obtain information about the shadow shape of the artificial valve as shape information related to the artificial valve. For example, the artificial neural network model may be a Mask R-CNN model. The Mask R-CNN model can use body X-ray images for heart training as training images of the Mask R-CNN model, and information on the type of artificial valve in the heart of the body X-ray image corresponding to each of the training body X-ray images. And shape information related to the artificial valve can be used as a mask of the Mask R-CNN model. For example, the artificial neural network model unit 120 may include a memory for storing instructions programmed to perform a function as an artificial neural network model, and a microprocessor for executing these instructions.

The processing unit 130 estimates the blood flow direction of the heart based on the shape information related to the artificial valve obtained by the artificial neural network model unit 120 , and the type and estimation of the artificial valve estimated by the artificial neural network model unit 120 . The type of artificial valve is determined as a result of re-estimating the type of artificial valve based on the direction of blood flow. For example, when estimating the blood flow direction, the processor 130 may estimate the blood flow direction of the heart based on a result of comparing the obtained shape information with preset shape information. For example, the preset shape information may be a plurality of crown shapes, and when estimating the blood flow direction, the processor 130 may estimate the blood flow direction for any one of the tissue valves respectively corresponding to the plurality of crown shapes. For example, the processing unit 130 performs a function of determining the type of artificial valve as a result of re-estimating the type of artificial valve based on the type of artificial valve estimated by the artificial neural network model unit 120 and the estimated blood flow direction. memory for storing instructions programmed to do so and a microprocessor for executing such instructions.

The output unit 140 outputs information on the type of artificial valve determined by the processing unit 130 . For example, the output unit 140 may output information about the type of artificial valve determined by the processing unit 130 so that it can be recognized from the outside. The output unit 140 may include a port for outputting information on the type of artificial valve, a wired communication module, or a wireless communication module. Alternatively, the output unit 140 may include an image display device capable of outputting information on the type of the artificial valve in the form of an image.

2 is a flowchart illustrating a process of learning an artificial neural network model of the artificial neural network model unit 120 of the medical image processing apparatus 100 according to a first embodiment of the present invention, and FIG. 3 is a first embodiment of the present invention. It is a flowchart illustrating a process in which the medical image processing apparatus 100 including the artificial neural network model learned according to the method determines the type of the artificial valve in the heart of the patient to be diagnosed.

Hereinafter, with reference to FIGS. 1 to 3 , the learning process for the artificial neural network model according to the first embodiment of the present invention, the process of determining the type of artificial valve using the learned artificial neural network model, etc. will be described in detail. .

First, the operator of the medical image processing apparatus 100 may prepare body X-ray images for learning of the heart as an input constituting the learning data set (S210), and the body X-ray image as a label constituting the learning data set information on the type of artificial valve in the heart and information on the shape related to the artificial valve may be prepared (S220). Here, the shape information related to the artificial valve included in the training data set as the label may be information about the shadow shape of the artificial valve.

When the thus prepared training data set is input through the input unit 110 , the artificial neural network model of the artificial neural network model unit 120 learns the training data set ( S230 ). In this way, the number of times the artificial neural network model unit 120 learns the training data set is not particularly limited, but as one embodiment, learning may be performed within an appropriate number of times for the best learning effect.

After learning of the artificial neural network model unit 120 of the medical image processing apparatus 100 is performed, an operator of the medical image processing apparatus 100 prepares a body X-ray image of a subject to be diagnosed and inputs it through the input unit 110 . can do.

Then, the artificial neural network model unit 120 learned through steps S210 to S230 estimates the type of artificial valve in the body X-ray image of the artificial neural network model from the body X-ray image of the diagnosis subject received through the input unit 110 . and acquires shape information related to the artificial valve. Here, the artificial neural network model unit 120 may acquire information about the shadow shape of the artificial valve as shape information related to the artificial valve ( S310 ).

Here, the type of artificial valve estimated by the artificial neural network model unit 120 through step S310 may or may not coincide with the actual type of the artificial valve existing in the body of the subject to be diagnosed. Several artificial valves existing in the body of the diagnosis subject may be included in the X-ray image in a similar position, or in the form of overlapping a plurality of artificial valves in a certain direction due to an enlarged heart or a change in body shape, in this case, in step S310 There is a relatively high probability that the type of artificial valves estimated by the researcher does not match the actual types of artificial valves present in the body compared to other examples.

Accordingly, the processing unit 130 of the medical image processing apparatus 100 estimates the blood flow direction of the heart based on the shape information related to the artificial valve obtained in step S310. Here, the reason that the processing unit 130 estimates the blood flow direction of the heart is to more accurately classify the types of artificial valves by reflecting the estimated blood flow direction of the heart. is likely to decrease.

The processing unit 130 compares the shape information related to the artificial valve acquired by the artificial neural network model unit 120 with preset shape information in step S310 to check whether the acquired shape information is included in the preset shape information. For example, the preset shape information may be a plurality of crown shapes, that is, various crown shapes. 5 is a view showing the shape of a shadow for each type of artificial valve. 5, it can be seen that among the tissue valves, the aortic valve (Aortic Bio), the pulmonary valve (Pulmonary Bio), the mitral valve (Mitral Bio), and the tricuspid valve (Tricuspid Bio) have a crown-shaped shadow.

Next, the processing unit 130 estimates the blood flow direction of the heart based on a result of comparing the shape information related to the artificial valve acquired by the artificial neural network model unit 120 with preset shape information in step S310 . For example, whether the blood flows from the lower side to the upper right side of the heart or the blood flow from the right side to the left side of the heart may be estimated according to which crown shape among the plurality of crown shapes ( S320 ).

Next, the processing unit 130 re-estimates the type of the artificial valve in the heart of the body X-ray image input in step S310 based on the type of artificial valve estimated in step S310 and the blood flow direction estimated in step S320. to determine the type of artificial valve. If it is confirmed in step S320 that the shape information related to the artificial valve is not included in the preset shape information, the result estimated in step S310 is finally determined as the type of the artificial valve as it is. However, when it is confirmed in step S320 that the shape information related to the artificial valve is included in the preset shape information, the type of the artificial valve can be corrected by reflecting the estimated blood flow direction instead of using the result estimated in step S310 as it is. . For example, when the blood flow flowing from the lower side to the upper right side of the heart is estimated, the type of the artificial valve may be finally determined as the aortic valve regardless of the estimation result of step S310, and the blood flow estimated as the blood flow from the right side to the left side of the heart In this case, the type of the artificial valve may be finally determined as the tricuspid valve regardless of the estimation result of step S310 (S330).

Thereafter, the output unit 140 outputs information on the type of the artificial valve determined by the processing unit 130 . For example, the output unit 140 outputs information on the type of artificial valve determined by the processing unit 130 in the form of an externally recognizable image, or as a separate electronic device through a wired communication module or a wireless communication module. can send

<Second embodiment>

The second embodiment can be said to be a case in which the artificial neural network model unit 120 performs until the processing unit 130 re-estimates the type of the artificial valve in the heart in the first embodiment.

FIG. 1 shows a configuration of a medical image processing apparatus 100 according to an exemplary embodiment, but what is shown in FIG. 1 is merely exemplary. The medical image processing apparatus 100 may be implemented in a PC or a server or may include the same.

Referring to FIG. 1 , the medical image processing apparatus 100 includes an input unit 110 , an artificial neural network model unit 120 , a processing unit 130 , and an output unit 140 .

The input unit 110 receives body X-ray images for heart training as an input constituting the first training data set. In addition, the input unit 110 receives type information of the artificial valve in the heart of the body X-ray image and shape information related to the artificial valve as a label constituting the first learning data set. In addition, the input unit 110 receives a plurality of shape information and cardiac blood flow direction information corresponding to the plurality of shape information as inputs constituting the second learning data set. In addition, the input unit 110 receives the type information of the artificial valve corresponding to a plurality of shape information and cardiac blood flow direction information as a label constituting the second learning data set. For example, the shape information related to the artificial valve included as a label of the first training data set may be information about the shadow shape of the artificial valve. In addition, the plurality of shape information may be a plurality of crown shapes, and the heart blood flow direction information may be a blood flow direction for any one of the tissue valves respectively corresponding to the plurality of crown shapes. Also, the input unit 110 receives a body X-ray image of the heart of the subject to be diagnosed. Here, the first training data set and the second training data set are to be used when training the artificial neural network model unit 120 , and the body X-ray image of the heart of the subject to be diagnosed is the previously learned artificial neural network model unit 120 . ) to determine the type of artificial valve.

In the artificial neural network model unit 120 , the first layer of the artificial neural network model learns the first training data set input through the input unit 110 , and uses the second learning data set input through the input unit 110 to model the artificial neural network model. The second layer of And, the artificial neural network model unit 120 including the learned artificial neural network model is the first layer of the artificial neural network model from the body X-ray image of the subject to be diagnosed, input through the input unit 110, of the artificial valve in the body X-ray image. Estimate the type and obtain information about the shape related to the artificial valve. Then, the second layer of the artificial neural network model estimates the blood flow direction of the heart based on the obtained shape information related to the artificial valve, and the first layer estimates the type of artificial valve and the estimated blood flow direction of the artificial valve. As a result of re-estimating the type, the type of artificial valve is determined. For example, the artificial neural network model may be a Mask R-CNN model. For example, the artificial neural network model unit 120 may include a memory for storing instructions programmed to perform a function as an artificial neural network model, and a microprocessor for executing these instructions.

The processing unit 130 controls the output unit 140 to output the type of artificial valve determined by the artificial neural network model unit 120 . For example, the processing unit 130 may include a microprocessor that executes various instructions.

The output unit 140 outputs information on the type of the artificial valve under the control of the processing unit 130 . For example, the output unit 140 may output information about the type of artificial valve determined by the processing unit 130 so that it can be recognized from the outside. The output unit 140 may include a port for outputting information on the type of artificial valve, a wired communication module, or a wireless communication module. Alternatively, the output unit 140 may include an image display device capable of outputting information on the type of the artificial valve in the form of an image.

4 is a flowchart illustrating a process of learning the artificial neural network model of the artificial neural network model unit 120 of the medical image processing apparatus 100 according to the second embodiment of the present invention.

Hereinafter, with reference to FIGS. 1 and 4 , the learning process for the artificial neural network model according to the second embodiment of the present invention and the process of determining the type of artificial valve using the learned artificial neural network model will be described in detail. .

First, the operator of the medical image processing apparatus 100 may prepare body X-ray images for heart training as an input constituting the first learning data set (S410), and as a label constituting the first learning data set Information on the type of the artificial valve in the heart of the body X-ray image and information on the shape related to the artificial valve may be prepared ( S420 ). Here, the shape information related to the artificial valve included in the training data set as the label may be information about the shadow shape of the artificial valve.

In addition, the operator of the medical image processing apparatus 100 may prepare a plurality of shape information and cardiac blood flow direction information corresponding to the plurality of shape information as an input constituting the second learning data set (S430), and the second As a label constituting the learning data set, information on types of artificial valves corresponding to a plurality of shape information and cardiac blood flow direction information may be prepared ( S440 ).

When the first training data set and the second training data set prepared in this way are input through the input unit 110, the first layer of the artificial neural network model learns the first training data set, and the second training data set of the artificial neural network model The second layer learns. In this way, the number of times the artificial neural network model unit 120 learns the training data set is not particularly limited, but as one embodiment, learning may be performed within an appropriate number of times for the best learning effect (S450).

After learning of the artificial neural network model unit 120 of the medical image processing apparatus 100 is performed, an operator of the medical image processing apparatus 100 prepares a body X-ray image of a subject to be diagnosed and inputs it through the input unit 110 . can do.

Then, the artificial neural network model unit 120 learned through steps S410 to S450 determines the type of artificial valve in the body X-ray image by the artificial neural network model from the body X-ray image of the diagnosis subject received through the input unit 110 . do. The process of the artificial neural network model unit 120 determining the type of artificial valve in the body X-ray image is that steps S310 to S330 of the first embodiment are sequentially performed by the first layer and the second layer of the artificial neural network model. Since it can be done and can be inferred from the above descriptions, a detailed description thereof will be omitted.

Thereafter, the output unit 140 outputs information on the type of artificial valve determined by the artificial neural network model unit 120 under the control of the processing unit 130 . For example, the output unit 140 outputs information on the type of artificial valve determined by the processing unit 130 in the form of an externally recognizable image, or as a separate electronic device through a wired communication module or a wireless communication module. can send

On the other hand, each step included in the medical image learning method and the medical image processing method according to the first and second embodiments described above is performed in a computer-readable recording medium for recording a computer program programmed to perform these steps. can be implemented.

In addition, each step included in the medical image learning method and the medical image processing method according to the above-described first and second embodiments is a computer program stored in a computer-readable recording medium programmed to perform these steps. It can be implemented in the form

Combinations of each step in each flowchart attached to the present invention may be performed by computer program instructions. These computer program instructions may be embodied in a processor of a general purpose computer, special purpose computer, or other programmable data processing equipment, such that the instructions performed by the processor of the computer or other programmable data processing equipment provide the functions described in each step of the flowchart. It creates a means to do these things. These computer program instructions may also be stored in a computer-usable or computer-readable medium that may direct a computer or other programmable data processing equipment to implement a function in a particular manner, and thus the computer-usable or computer-readable medium. The instructions stored in the recording medium are also capable of producing an article of manufacture including instruction means for performing the functions described in each step of the flowchart. The computer program instructions may also be mounted on a computer or other programmable data processing equipment, such that a series of operational steps are performed on the computer or other programmable data processing equipment to create a computer-executed process to create a computer or other programmable data processing equipment. It is also possible that instructions for performing the processing equipment provide steps for performing the functions described in each step of the flowchart.

Further, each step may represent a module, segment, or portion of code comprising one or more executable instructions for executing the specified logical function(s). It should also be noted that in some alternative embodiments it is also possible for the functions recited in the steps to occur out of order. For example, it is possible that two steps shown one after another may in fact be performed substantially simultaneously, or that the steps may sometimes be performed in the reverse order depending on the function in question.

The above description is merely illustrative of the technical idea of the present invention, and various modifications and variations will be possible without departing from the essential quality of the present invention by those skilled in the art to which the present invention pertains. Therefore, the embodiments disclosed in the present invention are not intended to limit the technical spirit of the present invention, but to explain, and the scope of the technical spirit of the present invention is not limited by these embodiments. The protection scope of the present invention should be construed by the following claims, and all technical ideas within the scope equivalent thereto should be construed as being included in the scope of the present invention.

100: medical image processing device
110: input unit
120: artificial neural network model unit
130: processing unit
140: output unit

Claims (13)

A medical image processing method performed by a medical image processing apparatus, comprising:
By inputting a body X-ray image of the heart of a subject to be diagnosed into a pre-trained artificial neural network model, the type of artificial valve in the heart of the body X-ray image is estimated as an output of the artificial neural network model, and the artificial valve and obtaining relevant shape information;
estimating the blood flow direction of the heart based on the obtained shape information;
determining the type of the artificial valve as a result of re-estimating the type of the artificial valve based on the estimated type of the artificial valve and the estimated blood flow direction;
Medical image processing method. The method of claim 1,
The step of obtaining the shape information includes obtaining information about the shadow shape of the artificial valve.
Medical image processing method. The method of claim 1,
The estimating of the blood flow direction includes comparing the acquired shape information with preset shape information;
estimating the blood flow direction of the heart based on the result of the comparison
Medical image processing method. 4. The method of claim 3,
The preset shape information is a plurality of crown shapes,
The step of estimating the blood flow direction includes estimating the blood flow direction for any one of the tissue valves respectively corresponding to the plurality of crown shapes.
Medical image processing method. As a computer-readable recording medium storing a computer program,
The computer program, when executed by a processor,
A computer-readable recording medium comprising instructions for causing the processor to perform the method according to any one of claims 1 to 4. As a computer program stored in a computer-readable recording medium,
The computer program, when executed by a processor,
A computer program comprising instructions for causing the processor to perform a method according to any one of claims 1 to 4. A medical image learning method of a medical image processing device, comprising:
Preparing body X-ray images for heart training as an input constituting a first training data set;
preparing information on types of artificial valves corresponding to each of the body X-ray images for learning and shape information related to the artificial valves as labels constituting the first learning data set;
Preparing a plurality of shape information and cardiac blood flow direction information corresponding to the plurality of shape information as inputs constituting a second learning data set;
preparing information on the type of artificial valve corresponding to the plurality of shape information and the cardiac blood flow direction information as a label constituting the second learning data set;
using the first training data set to train a first layer of the artificial neural network model, and using the second training data set to train a second layer of the artificial neural network model.
How to learn medical imaging. 8. The method of claim 7,
The shape information related to the artificial valve is information about the shadow shape of the artificial valve.
How to learn medical imaging. 8. The method of claim 7,
A plurality of shape information used as an input of the second training data set is a plurality of crown shapes, and the type information of the artificial valve used as a label of the second training data set is tissue valve type information.
How to learn medical imaging. As a computer-readable recording medium storing a computer program,
The computer program, when executed by a processor,
10. A computer-readable recording medium comprising instructions for causing the processor to perform the method according to any one of claims 7 to 9. As a computer program stored in a computer-readable recording medium,
The computer program, when executed by a processor,
A computer program comprising instructions for causing the processor to perform a method according to any one of claims 7 to 9. An input unit for receiving an X-ray image of the body of the subject to be diagnosed;
an artificial neural network model unit in which an artificial neural network model estimates the type of artificial valve in the body X-ray image from the body X-ray image of the diagnosis subject received through the input unit, and obtains shape information related to the artificial valve;
The blood flow direction of the heart is estimated based on the obtained shape information, and the type of the artificial valve is determined as a result of re-estimating the type of the artificial valve based on the estimated type of the artificial valve and the estimated blood flow direction. a processing unit that
Comprising an output unit for outputting information about the type of the artificial valve determined by the processing unit
Medical image processing device. A first learning data set including body X-ray images for learning of the heart as input, type information of an artificial valve corresponding to each of the learning body X-ray images, and shape information related to the artificial valve as a label and a second piece of information including a plurality of shape information and cardiac blood flow direction information corresponding to the plurality of shape information as inputs, and including the plurality of shape information and type information of an artificial valve corresponding to the cardiac blood flow direction information as a label an input unit for receiving a training data set;
An artificial neural network in which a first layer of an artificial neural network model learns the first training data set received through the input unit, and a second layer of the artificial neural network model learns the second training data set input through the input unit including the model
Medical image processing device.

Images